Re:When ChatGPT summarises, it does nothing of the kind
by paulmooreparks on Tuesday July 23, 2024 @04:48AM
(#41044015)
In the comments, the author clarified that he used GPT-4 for the article.
> What the colleague used, I can ask, but I suspect standard ChatGPT based on GPT-4. But my test was with GPT-4 (current standard), so that would mean about 8000 tokens (or roughly 4000 words, I think?). That may have influenced the result.
> What the colleague used, I can ask, but I suspect standard ChatGPT based on GPT-4. But my test was with GPT-4 (current standard), so that would mean about 8000 tokens (or roughly 4000 words, I think?). That may have influenced the result.